Speech & Audio

Unified Text and Speaker Verification using SSL model for Text-Dependent Speaker Verification Interspeech 2025 Unified Variational and Physics-aware Model for Room Impulse Response Estimation Interspeech 2025 Unifying Listener Scoring Scales: Comparison Learning Framework for Speech Quality Assessment and Continuous Speech Emotion Recognition Interspeech 2025 Unifying Streaming and Non-streaming Zipformer-based ASR ACL 2025 Universal Preference-Score-based Pairwise Speech Quality Assessment Interspeech 2025 Universal Semantic Disentangled Privacy-preserving Speech Representation Learning Interspeech 2025 Universal Speech Enhancement with Regression and Generative Mamba Interspeech 2025 Uni-VERSA: Versatile Speech Assessment with a Unified Network Interspeech 2025 UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation ICLR 2025 Unlearning LLM-Based Speech Recognition Models Interspeech 2025 Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate Interspeech 2025 Unmasking real-world audio deepfakes: A data-centric approach Interspeech 2025 Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech Interspeech 2025 URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Models EMNLP 2025 Using gender, phonation and age to interpret automatically discovered speech attributes for explainable speaker recognition Interspeech 2025 Using Neurogram Similarity Index Measure (NSIM) to Model Hearing Loss and Cochlear Neural Degeneration Interspeech 2025 VALLR: Visual ASR Language Model for Lip Reading ICCV 2025 Variability in Intervocalic /t/ and Community Diversity in Australian English Interspeech 2025 Variability in performance across four generations of automatic speaker recognition systems Interspeech 2025 VCapAV: A Video-Caption Based Audio-Visual Deepfake Detection Dataset Interspeech 2025 VERSA: A Versatile Evaluation Toolkit for Speech, Audio, and Music NAACL 2025 Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement ICLR 2025 VIB-based Real Pre-emphasis Audio Deepfake Source Tracing Interspeech 2025 VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversion Interspeech 2025 ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition Interspeech 2025